© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105372
    Prev
    Next
    INDEX
    Explanations

    phrases related to permission and restrictions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     cuál
    -0.51
     problemet
    -0.48
     toiminta
    -0.47
     Hva
    -0.46
     rencont
    -0.45
     cuáles
    -0.44
     inversores
    -0.44
     rencontré
    -0.43
     Moscú
    -0.43
     rencontrer
    -0.42
    POSITIVE LOGITS
     Allowed
    1.00
     allowed
    0.93
    allowed
    0.92
     ALLOWED
    0.92
    Allowed
    0.81
    ALLOWED
    0.78
     permitted
    0.76
    permitted
    0.75
    extAlignment
    0.73
     Forbidden
    0.71
    Activations Density 0.015%

    No Known Activations